Causal-Forcing
Causal-Forcing uses Causal ODE or Causal Consistency Distillation to drive asymmetric DMD as a theoretically correct initialization for real-time interactive video generation.

Quick Start
T2V
uv sync --package flashdreams-causal-forcing --inexact
uv run --no-sync flashdreams-run-v2 \
t2v-causal-forcing-wan2.1-t2v-1.3b-chunkwise \
--output-path artifacts/causal-forcing.mp4 --timeout unbound -- \
--prompt "A cat surfing" --total-blocks 7
Demo Presets
T2V
| Preset | Description |
|---|---|
t2v-causal-forcing-wan2.1-t2v-1.3b-chunkwise |
Chunkwise Wan 2.1 1.3B T2V (len_t=3). |
t2v-causal-forcing-wan2.1-t2v-1.3b-framewise |
Framewise Wan 2.1 1.3B T2V (len_t=1). |
Developer Details
- Minimum VRAM: about 24 GB.
- PyTorch: 2.9 or newer.
Samples
image: https://raw.githubusercontent.com/thu-ml/Causal-Forcing/refs/heads/main/prompts/i2v/26-15/000001.png
Citation
If you use Causal-Forcing, please cite the original work:
@article{zhu2026causal,
title={Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation},
author={Zhu, Hongzhou and Zhao, Min and He, Guande and Su, Hang and Li, Chongxuan and Zhu, Jun},
journal={arXiv preprint arXiv:2602.02214},
year={2026}
}